Title :
On Rotation Invariant Texture Classification Using Two-Grid Coupled CNNs
Author :
Ungureanu, Paul ; David, Emilian ; Goras, Liviu
Author_Institution :
Fac. of Electron. & Telecommun., Tech. Univ. "Gh. Asachi", Iasi
Abstract :
This paper presents several results of rotation-invariant texture classification using a bank of 2D band-pass CNN filters with approximately circular frequency response. The filters are autonomous two grid coupled CNNs, capable of producing Turing patterns used in the central linear part of their characteristic. The classification performances of the CNN filters are compared with the performances of the ideal circular filters
Keywords :
band-pass filters; cellular neural nets; frequency response; image classification; image texture; Turing pattern; band-pass CNN filter; circular frequency response; ideal circular filter; rotation invariant texture classification; Band pass filters; Cellular neural networks; Differential equations; Filter bank; Frequency response; Image texture analysis; Neural networks; Nonlinear filters; Piecewise linear techniques; Seminars; CNN filters; Texture classification; circular filters;
Conference_Titel :
Neural Network Applications in Electrical Engineering, 2006. NEUREL 2006. 8th Seminar on
Conference_Location :
Belgrade, Serbia & Montenegro
Print_ISBN :
1-4244-0433-9
Electronic_ISBN :
1-4244-0433-9
DOI :
10.1109/NEUREL.2006.341169